Knowledge-Grounded Agentic Large Language Models for Multi-Hazard Understanding from Reconnaissance Reports

TL;DR

This paper presents MoRA-RAG, a knowledge-grounded LLM framework that improves multi-hazard understanding from reconnaissance reports by integrating dynamic retrieval, agentic chunking, and verification, significantly enhancing accuracy and reducing hallucinations.

Contribution

The paper introduces MoRA-RAG, a novel framework combining dynamic retrieval, agentic chunking, and verification to improve multi-hazard reasoning from unstructured disaster reports.

Findings

Achieves up to 94.5% accuracy in hazard reasoning tasks.

Outperforms zero-shot LLMs by 30% and state-of-the-art RAG by 10%.

Reduces hallucinations across various LLM architectures.

Abstract

Post-disaster reconnaissance reports contain critical evidence for understanding multi-hazard interactions, yet their unstructured narratives make systematic knowledge transfer difficult. Large language models (LLMs) offer new potential for analyzing these reports, but often generate unreliable or hallucinated outputs when domain grounding is absent. This study introduces the Mixture-of-Retrieval Agentic RAG (MoRA-RAG), a knowledge-grounded LLM framework that transforms reconnaissance reports into a structured foundation for multi-hazard reasoning. The framework integrates a Mixture-of-Retrieval mechanism that dynamically routes queries across hazard-specific databases while using agentic chunking to preserve contextual coherence during retrieval. It also includes a verification loop that assesses evidence sufficiency, refines queries, and initiates targeted searches when information remains incomplete. We construct HazardRecQA by deriving question-answer pairs from GEER reconnaissance reports, which document 90 global events across seven major hazard types. MoRA-RAG achieves up to 94.5 percent accuracy, outperforming zero-shot LLMs by 30 percent and state-of-the-art RAG systems by 10 percent, while reducing hallucinations across diverse LLM architectures. MoRA-RAG also enables open-weight LLMs to achieve performance comparable to proprietary models. It establishes a new paradigm for transforming post-disaster documentation into actionable, trustworthy intelligence for hazard resilience.